相关论文: Person Re-identification: Implicitly Defining the …

Prototypical network for Few shot learning tries to learn an embedding function in the encoder that embeds images with similar features close to one another in the embedding space. However, in this process, the support set samples for a…

Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian…

Re-identification of individual animals in images can be ambiguous due to subtle variations in body markings between different individuals and no constraints on the poses of animals in the wild. Person re-identification is a similar task…

Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols. Although accuracy is paramount, in certain scenarios interpretability is a must. Unfortunately, such…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Pedestrian attributes, e.g., hair length, clothes type and color, locally describe the semantic appearance of a person. Training person re-identification (ReID) algorithms under the supervision of such attributes have proven to be effective…

Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical for practical application. In this paper, we propose a…

Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. In person re-identification, a pedestrian is usually represented with features extracted from a rectangular image…

Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved. In…

Credit scoring models support loan approval decisions in the financial services industry. Lenders train these models on data from previously granted credit applications, where the borrowers' repayment behavior has been observed. This…

Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in…

Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity…

Decision-making in complex systems often relies on machine learning models, yet highly accurate models such as XGBoost and neural networks can obscure the reasoning behind their predictions. In operations research applications,…

Cross-dataset transfer learning is an important problem in person re-identification (Re-ID). Unfortunately, not too many deep transfer Re-ID models exist for realistic settings of practical Re-ID systems. We propose a purely deep transfer…

Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…

It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering…

Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep…

Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling…

The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the…

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation. Compared with the individual-level features learned by speaker…